This post shows how to convert the PLOS study (published 10 July 2026) on veterinarians’ KAP for lumpy skin disease (n=398) into actionable evidence with AI-enabled qualitative analysis. The original paper is at PLOS ONE. Key study numbers: 83.67% of vets had managed LSD, about 92% rely on clinical signs, 69% consider clinical diagnosis sufficient, and 62.06% flagged antibiotic use as an AMR risk. If you run field interviews, clinic logs, or mixed surveys on LSD or other emerging animal diseases, this post shows how to (1) surface differential-diagnosis confusion, (2) quantify stewardship narratives, and (3) produce reproducible, segment-level briefs in hours rather than weeks.
Key Takeaways
Evidano is an AI-powered qualitative data analysis platform that turns KAP surveys, interviews, and clinic notes into reproducible, stakeholder-ready evidence quickly. The PLOS KAP study (n=398) shows strong reliance on clinical signs, widespread diagnostic confusion, and notable antibiotic use, all of which qualitative analysis can unpack into actionable policy recommendations.
Use thematic coding and cross-segment comparisons to link vets’ diagnostic language to antibiotic prescribing rationales and target AMR stewardship and lab-confirmation campaigns.
- n=398 veterinarians were surveyed across 157 upazilas (data collected 28 July 2022–30 June 2023).
- About 92% of respondents identify LSD by characteristic skin nodules, 69% treat on clinical grounds, and 73.62% reported diagnostic confusion with similar conditions.
- 62.06% of respondents perceived antibiotic use as an AMR risk, and 75.28% linked LSD to the hot-humid season.
Findings snapshot
| Date / Item | Metric | Value | Source / Note |
|---|---|---|---|
| Study published | Date | 10 July 2026 | PLOS ONE |
| Sample | Veterinarians surveyed | 398 | Cross-sectional, July 2022–June 2023 |
| Clinical experience | Managed ≥1 LSD case | 83.67% | Self-reported |
| Diagnosis method | Cases diagnosed clinically | ≈92% | Characteristic skin nodules |
| Diagnostic confidence | Consider clinical signs sufficient | 69% | But 73.62% reported diagnostic confusion |
| Antibiotic stewardship | Recognize AMR risk from use | 62.06% | Perception-based |
| Seasonality | Link to hot-humid season | 75.28% | Veterinarian perception |
What the PLOS study actually did
The PLOS paper was a cluster-randomized cross-sectional KAP survey of early-career veterinarians across 157 upazilas in Bangladesh, with data collected 28 July 2022–30 June 2023. The questionnaire covered demographics, clinical recognition, differential diagnoses, treatment choices, and attitudes toward antimicrobial use, and the analysis used descriptive statistics and χ2/Fisher tests in R.
- n=398 respondents; the majority were aged 21–29 and recent graduates (65.82%).
- Diagnostic reliance: 92% identify LSD by nodules; 69% treat on clinical grounds though 73.62% report confusion with cowpox, papillomatosis, and similar conditions.
- Treatment heterogeneity: 60.05% prescribe antibiotics (often combined with antihistamines/NSAIDs); only 43.22% thought antibiotics were used rationally.
- Study limits: self-report bias, a skew toward fresh graduates, and no PCR-confirmed cases in the survey.
So what for qualitative researchers and policy teams
Why KAP interviews matter here
KAP interviews provide the perception data needed to explain why veterinarians default to particular treatments and diagnoses. The study reports aggregated percentages, and qualitative text from interviews or clinic notes reveals the reasons behind those numbers: why vets default to antibiotics, what triggers diagnostic uncertainty, and which local beliefs shape traditional remedies.
High-value analytic questions you should ask
Which clinical features reliably trigger antibiotic prescribing versus watchful waiting?
How does experience (cases seen) change language around diagnostic certainty?
Are specific regions or service modalities (field vs telemedicine) associated with reliance on clinical diagnosis?
Do more, faster with Evidano: operational mapping
Ingest & normalize
Evidano imports and normalizes interview transcripts, clinic notes, and the survey spreadsheet (n=398). Evidano auto-transcribes audio, applies custom dictionaries (for example, local veterinary terms and drug names), and redacts PII so teams can safely share datasets with stakeholders.
Standardize codes & scale coding
Evidano applies uploaded codebooks, using a hierarchical clinical-sign scoring model to label themes consistently across a corpus. Evidano uses AI-assisted coding to surface consistent theme labels (diagnostic confusion, antibiotic rationale, vaccine talk) and allows reviewers to lock codes for reproducibility.
Quantify narratives (themes + frequency)
Evidano generates thematic counts, co-occurrence networks, and cross-segment comparisons by region, experience, and service type. Evidano makes it possible to quantify how often 'secondary infection' is cited as the reason for antibiotics and which regions mention traditional remedies.
Rapid evidence for policy
Evidano produces stakeholder-ready outputs including frequency tables, top supporting quotes, and an executive brief tied to the PLOS findings. All exports are reproducible and traceable to original documents.
Security & compliance
Evidano encrypts data, uses proprietary models tuned for qualitative research, and does not use user data to train third-party models, which is critical for sensitive health and AMR work.
Two-week workflow to reproduce and extend the study (practical how-to)
This two-week workflow reproduces and extends the PLOS study into policy-ready insights.
- Day 0–2: Collect and upload materials, survey spreadsheet, audio interviews, and clinic notes. Set custom dictionary entries for local disease names and drug brands.
- Day 3–4: Auto-transcribe and clean transcripts; run initial thematic extraction to surface top mentions such as 'nodule', 'cowpox', and 'antibiotic'.
- Day 5–7: Import the PLOS clinical-sign scoring model as a hierarchical codebook; run batch AI-assisted coding and validate 20% of documents manually.
- Day 8–10: Run cross-segment analyses (region, years of experience, telemedicine vs field). Generate co-occurrence networks to identify common diagnostic confusions.
- Day 11–13: Draft a stakeholder brief with top 10 quotes, frequency tables, and targeted recommendations such as a lab-confirmation drive and AMR stewardship training.
- Day 14: Export a reproducible report and deliver interactive visualizations for decision-makers.
FAQ: qualitative analysis of LSD KAP
Can qualitative methods reduce diagnostic confusion reported in the paper?
Yes. Thematic coding and co-occurrence analysis identify the specific symptom clusters and phrasing that lead veterinarians to conflate LSD with cowpox or papillomatosis, which helps prioritize training topics.
How do you measure antimicrobial stewardship narratives?
Combine thematic labels (for example, 'prophylactic antibiotic' and 'secondary infection') with frequency and segment comparisons to identify hotspots where antibiotics are overused.
Is this safe for sensitive health data?
Yes. Evidano encrypts data, supports PII redaction during transcription, and does not share user data for third-party model training, making it suitable for research involving human or farm-level privacy concerns.
Wrapping up: what to do next
AI-enabled qualitative analysis converts perception data from KAP interviews and clinic logs into policy-ready insights quickly. Start by uploading a small pilot (10–30 transcripts plus your survey) to validate codes and extract the top stewardship and diagnostic confusion themes. For a guided trial that maps PLOS-style KAP outputs to stakeholder-ready briefs, Try Evidano for free.
- Quick win: map where antibiotics are being justified, and produce a short training brief targeting those reasons.
- Policy win: use cross-segment comparisons to target lab-confirmation campaigns during hot-humid months (study: 75.28% linked seasonality).
- Operational win: standardize the clinical sign scoring model in Evidano to harmonize diagnosis language across districts.